INDEX

Explanations

specific fragments or components of complex words and phrases, often related to names or designations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

licken

-0.17

eview

-0.17

coni

-0.16

ayar

-0.15

 Ð¿Ð¾ÑĤÐµÐ½

-0.15

.bz

-0.14

 Potential

-0.14

potential

-0.14

amarin

-0.14

Ð°ÑĤÐ¸Ð²

-0.14

POSITIVE LOGITS

vell

0.14

 ==============================================================

0.14

 FindObjectOfType

0.14

ÏĥÏĦÎ±Î½

0.13

PropTypes

0.13

aller

0.13

Ð»Ð°Ð´Ñĥ

0.13

 poÅĻad

0.13

áº£y

0.13

ored

0.13

Activations Density 0.041%

specific fragments or components of complex words and phrases, often related to names or designations

No Comments

No Known Activations